Abstract | ||
---|---|---|
We describe a novel approach to unsupervised learning of the events that make up a script, along with constraints on their temporal ordering. We collect natural-language descriptions of script-specific event sequences from volunteers over the Internet. Then we compute a graph representation of the script's temporal structure using a multiple sequence alignment algorithm. The evaluation of our system shows that we outperform two informed baselines. |
Year | Venue | Keywords |
---|---|---|
2010 | ACL | graph representation,novel approach,temporal structure,script knowledge,informed baselines,multiple sequence alignment algorithm,unsupervised learning,web experiment,natural-language description,script-specific event sequence |
Field | DocType | Volume |
Computer science,Unsupervised learning,Natural language processing,Artificial intelligence,Multiple sequence alignment,Graph (abstract data type),Machine learning,The Internet | Conference | P10-1 |
Citations | PageRank | References |
18 | 1.04 | 19 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Michaela Regneri | 1 | 143 | 7.44 |
Alexander Koller | 2 | 438 | 35.50 |
Manfred Pinkal | 3 | 1116 | 69.77 |